Qiushi-Skill is a collection of agent skills that turn dialectical materialist and practical philosophy into methods for investigating problems, identifying their central contradiction, testing conclusions, and continuing work. It is intended to guide AI agents through analysis and task execution. The catalogue entries are its skills, commands, hook, plugin, and agent components.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add HughYau/qiushi-skill --skill workflowsgit clone --depth 1 https://github.com/HughYau/qiushi-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hughyau/qiushi-skill/workflows)<a href="https://agentmods.dev/skills/hughyau/qiushi-skill/workflows"><img src="https://agentmods.dev/badge/skills/hughyau/qiushi-skill/workflows/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hughyau/qiushi-skill/workflows"><img src="https://agentmods.dev/badge/skills/hughyau/qiushi-skill/workflows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00157 | $0.01120 |
| Opus 5.5 | $0.00063 | $0.00448 |
| Sonnet 5.5 | $0.00031 | $0.00224 |
| Haiku 4.5 | $0.00016 | $0.00112 |
Grade A, and why
workflows scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
工作流组合
"政策和策略是党的生命，各级领导同志务必充分注意，万万不可粗心大意。"
方法论的威力在于以正确顺序组合。下面四条是模式，不是流水线：不需要的步骤可以跳过，但每一步的交接物必须写出来，下一步必须引用它。
选择
| 情况 | 模式 |
|---|---|
| 全新项目或领域，目标已知路径未知 | 1 启动 |
| 已知的疑难问题，根因或路径不清 | 2 攻坚 |
| 已有方案，效果不理想 | 3 迭代 |
| 阶段性节点，要复盘并重定方向 | 4 复盘 |
| 都不符 | 回到 arming-thought 路由表单独调用 |
模式 1：新项目启动
investigation-first → contradiction-analysis → spark-prairie-fire → protracted-strategy
| 步 | 交接物 | 终止条件 |
|---|---|---|
| 调查 | 调查结论：现状 / 约束 / 未知 / 可依托基础 | 能回答"现在是什么情况" |
| 矛盾 | 主要矛盾 + 最值得突破的切入点 | 有一个明确切入点 |
| 星火 | 根据地 + 三步路线图 | 路线从当前能力出发 |
| 持久 | 当前阶段 + 转换条件 | 有阶段定位 |
模式 2：复杂问题攻坚
investigation-first → contradiction-analysis → concentrate-forces → practice-cognition（循环）→ criticism-self-criticism
| 步 | 交接物 | 终止条件 |
|---|---|---|
| 调查 | 现象 / 出现条件 / 已排除原因 / 未查方向 | 能精确描述问题，而非"好像是 X" |
| 矛盾 | 主要矛盾 + 可证伪假说 + 验证方式 | 有可验证假说 |
| 集中 | 🎯 主攻 = 验证该假说；暂缓其他 | 假说被证实或证伪 |
| 实践 | 判定 + 本轮学到；证伪则回到矛盾 | 问题彻底解决，能说清原因与解法 |
| 批评 | 工作审视报告 | 报告完成 |
模式 3：方案迭代优化
mass-line → contradiction-analysis → practice-cognition → criticism-self-criticism → mass-line（下一轮）
| 步 | 交接物 | 终止条件 |
|---|---|---|
| 群众 | ≥ 2 个来源的反馈、分歧、共同指向 | 至少两个独立来源 |
| 矛盾 | 本轮主要矛盾 + 改进假说 | 假说可验证 |
| 实践 | 改进结果 vs 指标 | 开始前写明的指标达到 |
| 批评 | 审视报告 | 报告完成 |
整体终止：反馈显示无新的重要问题，或用户确认。
模式 4：阶段复盘
criticism-self-criticism → contradiction-analysis → protracted-strategy（或 overall-planning）
| 步 | 交接物 | 终止条件 |
|---|---|---|
| 批评 | 审视报告：完成情况 / 问题 / 根因 | 报告完成 |
| 矛盾 | 下一阶段的主要矛盾 | 主要矛盾唯一 |
| 持久 / 统筹 | 新阶段定位与核心任务，或重新平衡的方案 | 有下一阶段核心任务 |
中断处理
- 信息不足 → 插入一次
investigation-first - 假说被证伪 → 回到
contradiction-analysis - 冒出更重要的矛盾 →
overall-planning评估是否调整整个模式 - 循环超出开始前声明的轮数 → 停下，向用户汇报现状
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · -150 lines · +40 tokens per session f66152355c32
- 1mo ago First seen · 226 lines · 117 tokens per session scan A a61801e772df
workflows is a skill published in the GitHub repository HughYau/qiushi-skill (3,832 stars, last pushed 27d ago), licensed MIT. It adds 157 tokens to every session and 1,120 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pentest-playbook
7-phase pentest pipeline from passive recon to exploitation.
to-issues
A planning aid that breaks a PRD or technical specification into small implementation issues, each covering a complete, demonstrable piece of work.
article-icons
A tool that adds static inline SVG icons from itshover.com to Markdown, HTML, and similar articles.
fix-pr-review-loop
Use when the user asks to fix a PR review and drive it to approval autonomously — "fix the PR review and loop until approved", "fix-pr-review-loop", "keep addressing review comments until this PR is approved". Takes an optional PR number/URL (defaults to the current branch's PR). Repeatedly calls fix-pr-review, waits…
expo-app-initialize
Scaffolds a new Expo React Native app with the tabs template, expo-router, react-native-mmkv, expo-dev-client, and expo-iap at their latest compatible versions using Bun, then runs prebuild and writes the project CLAUDE.md commands. Invoke only with /expo-app-initialize .
vaultr-compile-note
Compiles a single raw Vaultr note into knowledge units using a two-phase AI process (triage → compile). Use this skill whenever the user wants to compile a note into knowledge, extract knowledge from a note, update the knowledge base from a note, merge note content into knowledge units, or run knowledge compilation.…